CN110399763A - Face identification method and system - Google Patents

Face identification method and system Download PDF

Info

Publication number
CN110399763A
CN110399763A CN201810375426.3A CN201810375426A CN110399763A CN 110399763 A CN110399763 A CN 110399763A CN 201810375426 A CN201810375426 A CN 201810375426A CN 110399763 A CN110399763 A CN 110399763A
Authority
CN
China
Prior art keywords
face
local
terminal
image
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201810375426.3A
Other languages
Chinese (zh)
Other versions
CN110399763B (en
Inventor
黄源浩
江隆业
彭勋录
司马潇
许星
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Orbbec Co Ltd
Original Assignee
Shenzhen Orbbec Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Orbbec Co Ltd filed Critical Shenzhen Orbbec Co Ltd
Priority to CN201810375426.3A priority Critical patent/CN110399763B/en
Publication of CN110399763A publication Critical patent/CN110399763A/en
Application granted granted Critical
Publication of CN110399763B publication Critical patent/CN110399763B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31User authentication
    • G06F21/32User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401Transaction verification
    • G06Q20/4014Identity check for transactions
    • G06Q20/40145Biometric identity checks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161Detection; Localisation; Normalisation
    • G06V40/166Detection; Localisation; Normalisation using acquisition arrangements
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172Classification, e.g. identification

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Security & Cryptography (AREA)
  • Business, Economics & Management (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computer Hardware Design (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses a kind of face identification method and systems, this method comprises: acquisition active user's facial image;Obtain local motion end message collection;Face image set is referred to according to global information of mobile terminal collection and its corresponding overall situation, obtains local-reference face image set corresponding with the local motion end message collection;Active user's facial image is matched with the local-reference facial image to carry out recognition of face.By obtaining local motion end message collection, and face image set is referred to according to global information of mobile terminal collection and its corresponding overall situation, local-reference face image set corresponding with the local motion end message collection is obtained, so that the huge overall situation of data volume is contracted to the small local-reference face image set of data volume with reference to face image set.Recognition of face efficiency and precision can be substantially improved in this method, while not needing user and being actively entered corresponding identity information, improve user experience.

Description

Face identification method and system
Technical field
The present invention relates to computer and electronic apparatus application technical field more particularly to a kind of face identification method be System.
Background technique
Recognition of face gradually enters into daily life, for example is applied in multiple fields such as safety check, traffic.Face The key problem of identification is how to improve accuracy of identification and recognition rate, with identification hardware and the continuous hair of recognizer Exhibition, face recognition application field is also more and more extensive, for example consumer level depth camera and the maturation of deep learning algorithm are given Payment brings the high 3D face payment scheme of safety.
Recognition of face can be divided into 1v 1 identification and 1v N identification, wherein 1v 1 identification i.e. judge current face (1) and Pre-stored single refer to face (1) is compared, and 1v N identification is then to judge current face (1) and pre-stored N It is a to be compared with reference to face (N), to find target face identical with current face.1v1 is identified, is either known at present Other precision and recognition rate can reach commercial horizontal, and 1vN is identified, when N reaches hundreds of thousands or millions of even higher Quantity when, either accuracy of identification and recognition rate are unable to reach commercial level.
Summary of the invention
It is identified for 1v N, the present invention proposes a kind of face identification method and system, and recognition of face can be substantially improved Rate and precision, and user experience is high.
Face identification method provided by the invention, comprising: acquisition active user's facial image;Obtain local motion terminal letter Breath collection;Face image set is referred to according to global information of mobile terminal collection and its corresponding overall situation, is obtained whole with the local motion The corresponding local-reference face image set of client information collection;By active user's facial image and the local-reference facial image It is matched to carry out recognition of face.
In some embodiments, the equipment for obtaining local motion end message collection includes: base station, WIFI equipment, indigo plant One of tooth equipment and GPS device are a variety of;The facial image includes color image, infrared image, gray level image and depth Spend one of image or a variety of.
In some embodiments, this method further include: being executed according to face recognition result includes face unlock, face branch It pays, one of tasks such as face safety check or a variety of.
The present invention also provides a kind of face identification systems, comprising: man face image acquiring terminal, for acquiring active user people Face image;Positioning terminal, for obtaining the local motion end message collection comprising active user in coverage area;Server, For storing global information of mobile terminal collection and its corresponding overall situation with reference to face image set;Processor is used for: according to described complete Office's information of mobile terminal collection and the overall situation refer to face image set, obtain office corresponding with the local motion end message collection Portion refers to face image set, and, active user's facial image is matched with the local-reference facial image with Carry out recognition of face.
In further embodiments, face identification system provided by the invention, comprising: positioning terminal;Man face image acquiring Terminal, for acquiring active user's facial image and extracting the positioning terminal id information;Server, for storing global shifting Dynamic end message collection and its corresponding overall situation refer to face image set;Processor is used for: according to the positioning terminal id information, Oriented from the global information of mobile terminal concentration have information of mobile terminal identical with the positioning terminal id information from And local motion end message collection is formed, while will all ginsengs corresponding with local motion end message concentration information of mobile terminal It examines facial image and forms local-reference face image set, and, by active user's facial image and the local-reference people Face image is matched to carry out recognition of face.
In some embodiments, the processor is also used to, paid based on face recognition result execution including face, One of tasks such as face unlock, face safety check are a variety of.
Beneficial effects of the present invention: by obtaining local motion end message collection, and according to global information of mobile terminal collection And its it is corresponding global with reference to face image set, obtain local-reference face figure corresponding with the local motion end message collection Image set, so that the huge overall situation of data volume is contracted to the small local-reference face image set of data volume with reference to face image set; Active user's facial image is matched with local-reference face image set to carry out recognition of face again, people can be substantially improved Face recognition efficiency and precision, while not needing user and being actively entered corresponding identity information, improve user experience.
Detailed description of the invention
Fig. 1 is face identification system schematic diagram in the prior art.
Fig. 2 is the face identification system schematic diagram according to one embodiment of the invention.
Fig. 3 is the face identification method schematic diagram according to one embodiment of the invention.
Specific embodiment
With reference to embodiment and compares attached drawing invention is further described in detail, it should be emphasised that, Following the description is only exemplary, the range and its application being not intended to be limiting of the invention.
Face identification system in the prior art is as shown in Figure 1, mainly include server and man face image acquiring terminal.Its In, server is preserved a large amount of (for example quantity is M) and be can wrap with reference to facial image and its corresponding identity information, identity information It includes: one of account, title, identification card number, information of mobile terminal (such as cell-phone number) or a variety of combinations.Man face image acquiring Terminal contains the camera for acquiring active user's facial image.In addition to this, it is gone back in server or man face image acquiring terminal Memory etc. further containing processor and the application program for being stored with recognition of face task, to carry out recognition of face.In In one embodiment, server is Alipay cloud server, and man face image acquiring terminal is to be equipped with Alipay payment terminals to answer With the Intelligent hardware of program.
When user needs to carry out recognition of face task, such as brush face payment/unlock, safety check reach a standard, in the prior art for The recognition rate and accuracy of identification for improving face identification system, by user to be identified to system input identity information Afterwards, 1v 1 is converted by 1v N identification to identify, mainly include following steps:
Firstly, when user is by face (lower to be known as current face) close man face image acquiring terminal, inner camera acquisition The facial image of current face, camera here can be two-dimensional camera and be also possible to three-dimensional depth camera, and facial image can be with It is one of color image, infrared image, gray level image, depth image etc. or a variety of, in one embodiment, camera is RGBD camera, the collected current face's image of institute includes depth image and color image, i.e. RGBD image.
Secondly, user inputs corresponding identity information to man face image acquiring terminal, for example, account, title, identification card number, Information of mobile terminal (such as cell-phone number).After getting identity information, man face image acquiring terminal arrives identity information feedback Server, and extract user corresponding with the identity information from server and refer to facial image.It should be noted that server As background end, in advance by the modes such as Account Registration, real-name authentication save magnanimity (being assumed to be M) identity information and Its is corresponding with reference to facial image, for example the upload of facial image is realized by individual mobile terminal;The quantity of M can be thousand Ten thousand grades even hundred million grades.
Finally, the processor in server or man face image acquiring terminal executes current face's image and refers to facial image Recognition of face task, matched including being identified to current face's image with feature extraction and the feature with reference to facial image.
After identifying successfully, man face image acquiring terminal can also further execute follow-up work, for example safety check is appointed Rays safety detection apparatus is then controlled for business allows user to pass through;And payment task is then executed accordingly withhold operation and prompt payment at Function.User can also be prompted to input password further to ensure safety of payment when execution is withholdd and operated;Then for unlock task Control unlock.
In method as above, need user that input identity information is actively gone to go out and this in order to backstage (server) removal search Identity information is corresponding to refer to facial image, in order to the recognition of face of subsequent execution 1v1, to improve recognition efficiency and identification Precision.However, the shortcomings that this mode is poor user experience, it is almost like with traditional fingerprint recognition, two dimensional code identification process, The operation occupied time long and different user, the time of operation also difference;In addition, this is cumbersome, can not give User brings quick, convenient and fast experience.
To solve the above problems, the present embodiment provides a kind of face identification systems, as shown in Fig. 2, the system includes: service Device, man face image acquiring terminal and positioning terminal.
Server is stored with a large amount of (for example quantity is M) with reference to facial image and corresponding identity information, identity letter Breath may include: one of account, title, identification card number, information of mobile terminal (such as cell-phone number) or a variety of combinations, difference Identity information between mutually bind, it is final realize it is consistent;For ease of description, here will largely with reference to facial image and its Corresponding identity information is known as global with reference to face image set and global set of identity information (including global account's collection, global name Collection, global information of mobile terminal collection etc.).In some embodiments, server also includes processor, for carrying out data processing, For example execute face identification mission etc., it can also include communication interface.
Man face image acquiring terminal contains the camera for acquiring active user's facial image, what active user here referred to It is the target user in this recognition of face, camera can be two-dimensional camera and be also possible to three-dimensional depth camera, and facial image can To be one of color image, infrared image, gray level image, depth image etc. or a variety of, in one embodiment, camera is RGBD camera, the collected active user's facial image of institute includes depth image and color image, i.e. RGBD image, in a reality It applies in example, camera is structure light depth camera, and the collected active user's facial image of institute includes infrared structure light image, relatively It is implied with depth information in depth, gray scale, color image etc., infrared structure light image, while also including gray scale and cromogram Texture information as in, therefore can be reached simultaneously using infrared structure light image progress recognition of face with depth image and line Manage the double dominant of image.In some embodiments, man face image acquiring terminal also includes processor for carrying out at data Reason and control, for example execute face identification mission etc., can also include communication interface, in order to be communicated with server etc..
Positioning terminal is used to obtain the information of mobile terminal in its coverage area.Generally, by man face image acquiring terminal It is arranged in the coverage area of positioning terminal, when current user goes to carry out recognition of face, the available current use of positioning terminal The portable information of mobile terminal in family.It should be noted that often not only only having in the range of positioning terminal is covered Target user also has other users, therefore is comprising multiple mobile terminals including active user acquired in positioning terminal Information (is assumed to be N), for ease of description, will be known as local motion end comprising multiple information of mobile terminal including active user Client information collection.It is understood that local motion end message collection should be the subset of global information of mobile terminal collection.
Positioning terminal may include but be not limited to following several:
(1) base station
When mobile terminal enters in the range of base station covers, identification of base stations goes out information of mobile terminal, such as cell-phone number, Termination ID etc. (information of mobile terminal and face recognition application account are bound).The range radius covered by base station is often It is less, such as several hundred rice, therefore the number of users entered within the scope of this tends not to too much, such as thousands of or tens of thousands of etc..As a result, Positioning terminal can identify mobile terminal quantity (such as N) and corresponding information of mobile terminal within the scope of its, and will be mobile whole Client information is saved into its memory.
(2) WIFI equipment, such as WIFI transmitter
When mobile terminal enters in the range of the WIFI equipment covers, WIFI equipment identifies information of mobile terminal, And it saves into its memory.The range radius that usual WIFI equipment is covered is several meters to tens meters, and slightly smaller than base station is covered Lid range, therefore when WIFI equipment is as positioning terminal, the mobile terminal quantity in range can achieve it is several hundred even more It is few.
(3) bluetooth equipment
When mobile terminal enters in the range of the bluetooth equipment covers, bluetooth equipment identifies information of mobile terminal, And it saves into its memory.
(4) GPS device
After GPS device inside mobile terminal is opened, the i.e. identified positioning of mobile terminal, information of mobile terminal (including move The information such as account information, the position of dynamic terminal) it is stored in memory.It is different from base station, WIFI equipment, bluetooth equipment It is that the mobile terminal quantity that GPS device is stored is very huge, or even can is more than the mobile terminal quantity that server end saves. Therefore it when being positioned, often chooses certain region and is positioned, such as centered on man face image acquiring terminal, one Determine in the range of radius for localization region.
(5) base station, WIFI equipment, bluetooth equipment, two or more in GPS device.
The mobile terminal quantity that GPS device can identify is big, but is easy to be limited by cloud layer and shelter;Bluetooth equipment, The mobile terminal quantity that WIFI equipment can identify is relatively small, but is influenced by shelter smaller, and its is at low cost;Base station is set Relatively always for the mobile terminal quantity that can be identified, but its is at high cost.Therefore two or more among this several person are utilized, it can be with Overall cost and the accuracy for improving positioning.When positioning terminal is using two in base station, WIFI equipment, bluetooth equipment, GPS device When planting or is a variety of, the information of mobile terminal obtained can be the set of information of mobile terminal collection acquired in individual equipment, It can be the intersection of information of mobile terminal collection acquired in individual equipment.It is understood that positioning terminal may be other Have identify or positioning mobile terminal function equipment.
The effect of positioning terminal is that the mobile terminal in its coverage area is positioned and identified automatically, shifting here Dynamic terminal is usually that user carries and equipment corresponding with user identity, such as mobile phone, plate, apparatus such as computer.When with It when family carrying mobile terminal enters in the range of positioning terminal covers, will be identified by positioning terminal, positioning terminal can be right in real time Information of mobile terminal in its coverage area is updated in real time, it is believed that positioning terminal obtains its covering in real time The information of mobile terminal of all users in range, i.e. local motion end message collection.Generally, according to the similar of positioning terminal And the density of population, local motion end message concentrate the quantity of user also different, and as little as tens, it is up to tens of thousands of, but also much Less than the number of users that global information of mobile terminal concentrates ten million or excessively hundred million.
Contain one or more processors (sub-processor) in man face image acquiring terminal and/or server, for holding Pedestrian's face identification mission.In one embodiment, recognition of face task includes following steps, as shown in Figure 3:
S1. active user's facial image is acquired;
S2. local motion end message collection is obtained;
S3. face image set, acquisition and local motion are referred to according to global information of mobile terminal collection and its corresponding overall situation The corresponding local-reference face image set of end message collection;
S4. active user's facial image collected is matched with local-reference face image set to realize that face is known Not.
Step S1 as above is executed by the processor control camera in man face image acquiring terminal;Step S2 both can be by Positioning terminal executes, and can also be executed by server;Step S3 is executed by server;Step S4 can both be executed by server, It can also be executed by man face image acquiring terminal.System according to Fig.2, when step S2 and step S4 is by different terminal institutes When execution, detailed process difference.
In some embodiments, when by positioning terminal execute step S2, man face image acquiring terminal execute step S4 when, Detailed process is as follows:
S11. camera of the user in man face image acquiring terminal, processor control camera and acquire active user's face figure Picture.
S21. man face image acquiring terminal is communicated with the positioning terminal and server interconnection respectively.Positioning is eventually End real-time update enters the local motion end message collection in its coverage area, and man face image acquiring terminal handler is from positioning Local motion end message collection is read in terminal, and local motion end message collection is transmitted to server.
S31. after server receives local information of mobile terminal collection, by processor according to global information of mobile terminal collection and entirely Office refers to face image set, by modes such as matching search, finds and concentrates all mobile terminals to believe with local motion end message The corresponding local-reference facial image of breath, and form local-reference face image set.Then by local-reference face image set It is transmitted to man face image acquiring terminal.
S41. the processor in man face image acquiring terminal is by active user's facial image collected and local-reference people Face image collection is matched to realize recognition of face.For example judge whether active user concentrates in local-reference facial image, or Person concentrates the identity information (such as information of mobile terminal) etc. of confirmation active user from local-reference facial image.
In further embodiments, when by positioning terminal execution step S2, when server executes step S4, detailed process It is as follows:
S12. the processor control camera in man face image acquiring terminal acquires active user's facial image and is sent to clothes Business device.
S22. man face image acquiring terminal is communicated with the positioning terminal and server interconnection respectively;Positioning is eventually End real-time update enters the local motion end message collection in its coverage area, and the processor of man face image acquiring terminal is from calmly Local motion end message collection is read in the terminal of position, and local motion end message collection is transmitted to server.
S32. after server receives local information of mobile terminal collection, by processor according to global information of mobile terminal collection and entirely Office refers to face image set, by modes such as matching search, finds and concentrates all mobile terminals to believe with local motion end message The corresponding local-reference facial image of breath, and form local-reference face image set.Then by local-reference face image set It is transmitted to man face image acquiring terminal.
S42. the processor in server active user's facial image is matched with local-reference face image set with It realizes recognition of face, and recognition result is sent to man face image acquiring terminal.
Compared with the prior art, without user above embodiment is manually entered identity information, but certainly by positioning terminal N number of first movement terminal entrained by the dynamic user identified in its coverage area, and then 1v M is converted to 1v N's Identification also can achieve high speed, high-precision recognition of face since the quantity of N is much smaller than the number of users of server end. Entire face recognition process only needs user by face against camera, and without other operation bidirectionals, experience effect is splendid.
In some embodiments, it is contemplated that the rights concerns of positioning terminal and man face image acquiring terminal, such as when positioning is whole When end by base station, recognition of face terminal is that common trade company possesses equipment, common trade company is often not directly from base station reading The permission of other users.It is then difficult to read the number of users within the scope of current base station from base station at this time, i.e., can not read part Information of mobile terminal collection.In order to solve this problem, in one embodiment, it is contemplated that mobile terminal possesses where reading itself The permission of base station information (such as base station IDs), thus when user carry mobile terminal enter where base station (or other positioning Terminal) in overlay area when, the ID of base station where mobile terminal will extract, while the base station IDs are reported into server.Service It then also include Base station ID information in device institute memory mobile terminal information.In addition, man face image acquiring terminal is also equipped with simultaneously Accordingly with the device of base station communication (such as SIM card and corresponding communication hardware), then man face image acquiring terminal can also With by identification of base stations, while man face image acquiring terminal can read base station IDs.When executing face identification mission, facial image Acquisition terminal will report to server based on the base station IDs being currently located, and server is reported according to current face's Image Acquisition terminal Base station IDs orient all information of mobile terminal under the ID, form local motion end message collection, while server also can Local-reference face image set corresponding with the local motion end message collection is generated, then by server or man face image acquiring Processor in terminal executes active user's facial image and the identification matching task with reference to face image set.Above procedure has more The step of body, is as follows:
S13. camera of the user in man face image acquiring terminal, processor control camera and acquire active user's face figure Picture.
S23. man face image acquiring terminal is communicated with server interconnection.Man face image acquiring terminal reads positioning Terminal ID info, and it is uploaded to server.
S33. it after server receives positioning terminal id information, concentrates and finds and the id information from global information of mobile terminal Identical all information of mobile terminal will be concentrated with local motion end message and be moved to form local motion end message collection Dynamic end message is corresponding all with reference to facial image formation local-reference face image set.Then by local-reference facial image Collection is transmitted to man face image acquiring terminal.
S43. the processor in man face image acquiring terminal is by active user's facial image collected and local-reference people Face image collection is matched to realize recognition of face.For example judge whether active user concentrates in local-reference facial image, or Person concentrates the identity information (such as information of mobile terminal) etc. of confirmation active user from local-reference facial image.
It is understood that recognition of face can also be executed directly by server in the present embodiment, server is by face Recognition result is sent to man face image acquiring terminal.
In some embodiments, it is also possible to determine by other means the local users in active user location Position, to reduce the matched object user's number of face.
Above-described facial image is interpreted as sensu lato facial image, either the people directly acquired by camera Face image can also carry out the eigenface after feature extraction to facial image, or be able to reflect other categories of face characteristic Property etc..
The above content is combine it is specific/further detailed description of the invention for preferred embodiment, cannot recognize Fixed specific implementation of the invention is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, Without departing from the inventive concept of the premise, some replacements or modifications can also be made to the embodiment that these have been described, And these substitutions or variant all shall be regarded as belonging to protection scope of the present invention.

Claims (10)

1. a kind of face identification method characterized by comprising
Acquire active user's facial image;
Obtain local motion end message collection;
Face image set is referred to according to global information of mobile terminal collection and its corresponding overall situation, is obtained and the local motion terminal The corresponding local-reference face image set of information collection;
Active user's facial image is matched with the local-reference facial image to carry out recognition of face.
2. face identification method as described in claim 1, which is characterized in that described to obtain setting for local motion end message collection Standby includes: one of base station, WIFI equipment, bluetooth equipment and GPS device or a variety of.
3. face identification method as described in claim 1, which is characterized in that the facial image includes color image, infrared One of image, gray level image and depth image are a variety of.
4. face identification method as described in claim 1, which is characterized in that further include: packet is executed according to face recognition result Include one of face unlock, face payment, face safety check task or a variety of.
5. a kind of face identification system characterized by comprising
Man face image acquiring terminal, for acquiring active user's facial image;
Positioning terminal, for obtaining the local motion end message collection comprising active user in coverage area;
Server, for storing global information of mobile terminal collection and its corresponding overall situation with reference to face image set;
Processor is used for:
Face image set is referred to according to the global information of mobile terminal collection and the overall situation, is obtained and the local motion terminal The corresponding local-reference face image set of information collection, and,
Active user's facial image is matched with the local-reference facial image to carry out recognition of face.
6. face identification system as claimed in claim 5, which is characterized in that the processor is also used to, and is based on recognition of face As a result execute includes one of face payment, face unlock, face safety check task or a variety of.
7. face identification system as claimed in claim 5, which is characterized in that the positioning terminal include base station, WIFI equipment, One of bluetooth equipment and GPS device are a variety of.
8. a kind of face identification system characterized by comprising
Positioning terminal;
Man face image acquiring terminal, for acquiring active user's facial image and extracting the positioning terminal id information;
Server, for storing global information of mobile terminal collection and its corresponding overall situation with reference to face image set;
Processor is used for:
According to the positioning terminal id information, orienting from the global information of mobile terminal concentration has and the positioning terminal The identical information of mobile terminal of id information, while will be with local motion end message collection to forming local motion end message collection Middle information of mobile terminal is corresponding all with reference to facial image formation local-reference face image set, and,
Active user's facial image is matched with the local-reference facial image to carry out recognition of face.
9. face identification system as claimed in claim 8, which is characterized in that the processor is also used to, and is based on recognition of face As a result execute includes one of face payment, face unlock, face safety check task or a variety of.
10. face identification system as claimed in claim 8, which is characterized in that the positioning terminal includes that base station, WIFI are set One of standby, bluetooth equipment and GPS device are a variety of.
CN201810375426.3A 2018-04-24 2018-04-24 Face recognition method and system Active CN110399763B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810375426.3A CN110399763B (en) 2018-04-24 2018-04-24 Face recognition method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810375426.3A CN110399763B (en) 2018-04-24 2018-04-24 Face recognition method and system

Publications (2)

Publication Number Publication Date
CN110399763A true CN110399763A (en) 2019-11-01
CN110399763B CN110399763B (en) 2023-04-18

Family

ID=68322318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810375426.3A Active CN110399763B (en) 2018-04-24 2018-04-24 Face recognition method and system

Country Status (1)

Country Link
CN (1) CN110399763B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111210375A (en) * 2019-11-27 2020-05-29 重庆特斯联智慧科技股份有限公司 Multi-functional portable wisdom security protection all-in-one
CN111639934A (en) * 2020-02-17 2020-09-08 ***股份有限公司 Payment method and payment device based on biological characteristic matching
CN113033466A (en) * 2021-04-13 2021-06-25 山东大学 Face recognition method and device
CN113255399A (en) * 2020-02-10 2021-08-13 北京地平线机器人技术研发有限公司 Target matching method and system, server, cloud, storage medium and equipment
CN113610071A (en) * 2021-10-11 2021-11-05 深圳市一心视觉科技有限公司 Face living body detection method and device, electronic equipment and storage medium
WO2023275606A1 (en) * 2021-06-30 2023-01-05 商汤国际私人有限公司 Facial recognition method, system and apparatus, and electronic device and storage medium
CN117542100A (en) * 2023-11-13 2024-02-09 以萨技术股份有限公司 Face information judging method, storage medium and electronic equipment

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747520A (en) * 2013-12-20 2014-04-23 百度在线网络技术(北京)有限公司 Positioning method and device for mobile terminal
CN103839161A (en) * 2014-03-24 2014-06-04 上海交通大学 System and method for authentication and transmission of mobile payment information
CN105279814A (en) * 2014-07-24 2016-01-27 中兴通讯股份有限公司 Driving recording treatment method and driving recording treatment system
WO2016023347A1 (en) * 2014-08-13 2016-02-18 惠州Tcl移动通信有限公司 Login method and system through human face recognition based on mobile terminal
WO2016206185A1 (en) * 2015-06-24 2016-12-29 中兴通讯股份有限公司 Unlocking method, device and terminal based on face recognition and storage medium
CN106778489A (en) * 2016-11-14 2017-05-31 深圳奥比中光科技有限公司 The method for building up and equipment of face 3D characteristic identity information banks
CN107169483A (en) * 2017-07-12 2017-09-15 深圳奥比中光科技有限公司 Tasks carrying based on recognition of face
CN107483416A (en) * 2017-07-27 2017-12-15 湖南浩丰文化传播有限公司 The method and device of authentication
CN107832598A (en) * 2017-10-17 2018-03-23 广东欧珀移动通信有限公司 Solve lock control method and Related product

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103747520A (en) * 2013-12-20 2014-04-23 百度在线网络技术(北京)有限公司 Positioning method and device for mobile terminal
CN103839161A (en) * 2014-03-24 2014-06-04 上海交通大学 System and method for authentication and transmission of mobile payment information
CN105279814A (en) * 2014-07-24 2016-01-27 中兴通讯股份有限公司 Driving recording treatment method and driving recording treatment system
WO2016023347A1 (en) * 2014-08-13 2016-02-18 惠州Tcl移动通信有限公司 Login method and system through human face recognition based on mobile terminal
WO2016206185A1 (en) * 2015-06-24 2016-12-29 中兴通讯股份有限公司 Unlocking method, device and terminal based on face recognition and storage medium
CN106778489A (en) * 2016-11-14 2017-05-31 深圳奥比中光科技有限公司 The method for building up and equipment of face 3D characteristic identity information banks
CN107169483A (en) * 2017-07-12 2017-09-15 深圳奥比中光科技有限公司 Tasks carrying based on recognition of face
CN107483416A (en) * 2017-07-27 2017-12-15 湖南浩丰文化传播有限公司 The method and device of authentication
CN107832598A (en) * 2017-10-17 2018-03-23 广东欧珀移动通信有限公司 Solve lock control method and Related product

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111210375A (en) * 2019-11-27 2020-05-29 重庆特斯联智慧科技股份有限公司 Multi-functional portable wisdom security protection all-in-one
CN113255399A (en) * 2020-02-10 2021-08-13 北京地平线机器人技术研发有限公司 Target matching method and system, server, cloud, storage medium and equipment
CN111639934A (en) * 2020-02-17 2020-09-08 ***股份有限公司 Payment method and payment device based on biological characteristic matching
CN113033466A (en) * 2021-04-13 2021-06-25 山东大学 Face recognition method and device
WO2023275606A1 (en) * 2021-06-30 2023-01-05 商汤国际私人有限公司 Facial recognition method, system and apparatus, and electronic device and storage medium
CN113610071A (en) * 2021-10-11 2021-11-05 深圳市一心视觉科技有限公司 Face living body detection method and device, electronic equipment and storage medium
CN117542100A (en) * 2023-11-13 2024-02-09 以萨技术股份有限公司 Face information judging method, storage medium and electronic equipment

Also Published As

Publication number Publication date
CN110399763B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
CN110399763A (en) Face identification method and system
JP6859521B2 (en) Payment methods, entrance control methods, and devices
US10157324B2 (en) Systems and methods of updating user identifiers in an image-sharing environment
CN104092692B (en) It is a kind of anonymous with servicing the location privacy protection method that similitude is combined based on k
US10282856B2 (en) Image registration with device data
CN108885698B (en) Face recognition method and device and server
CN107483416A (en) The method and device of authentication
CN107274278A (en) A kind of system of renting a house based on Internet of Things intelligent door lock
CN105590097B (en) Dual camera collaboration real-time face identification security system and method under the conditions of noctovision
CN207690169U (en) It can reservation type recognition of face gate inhibition's guest system
CN104167025A (en) Mobile attendance system based on dynamic face recognition and WIFI positioning and method of attendance system
CN106204948A (en) Locker management method and locker managing device
CN104582187A (en) Recording and lamplight control system and method based on face recognition and facial expression recognition
WO2018166291A1 (en) User sign-in identification method based on multifactor cross-verification
CN102819877A (en) Position-based attendance system and method
CN105393262A (en) Feature identification using an rgb-nir camera pair
CN110166525A (en) Resource information processing management system applied to garden
CN105791325A (en) Method and device for sending image
Jaikumar et al. Fingerprint based student attendance system with SMS alert to parents
Xu et al. SocioGlass: social interaction assistance with face recognition on *** glass
CN113516167A (en) Biological feature recognition method and device
CN103186590A (en) Method for acquiring identity information of wanted criminal on run through mobile phone
CN110375716B (en) Unmanned aerial vehicle searching information generation method and unmanned aerial vehicle
CN207601878U (en) Multifunctional intellectual remote door access system
CN105516922A (en) Method and system for positioning and finding based on smart wallet, and smart wallet

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 11-13 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Yuehai street, Nanshan District, Shenzhen, Guangdong 518000

Applicant after: Obi Zhongguang Technology Group Co.,Ltd.

Address before: 12 / F, joint headquarters building, high tech Zone, 63 Xuefu Road, Nanshan District, Shenzhen, Guangdong 518000

Applicant before: SHENZHEN ORBBEC Co.,Ltd.

GR01 Patent grant
GR01 Patent grant